Fast concurrent object localization and recognition
Object localization and recognition are important problems in computer vision. However, in many applications, exhaustive search over all object models and image locations is computationally prohibitive. While several methods have been proposed to make either recognition or localization more efficien...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2012
|
| Online Access: | http://hdl.handle.net/1721.1/74258 |
| _version_ | 1826216215107862528 |
|---|---|
| author | Yeh, Tom Lee, John J. Darrell, Trevor J. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Yeh, Tom Lee, John J. Darrell, Trevor J. |
| author_sort | Yeh, Tom |
| collection | MIT |
| description | Object localization and recognition are important problems in computer vision. However, in many applications, exhaustive search over all object models and image locations is computationally prohibitive. While several methods have been proposed to make either recognition or localization more efficient, few have dealt with both tasks simultaneously. This paper proposes an efficient method for concurrent object localization and recognition based on a data-dependent multi-class branch-and-bound formalism. Existing bag-of-features recognition techniques which can be expressed as weighted combinations of feature counts can be readily adapted to our method. We present experimental results that demonstrate the merit of our algorithm in terms of recognition accuracy, localization accuracy, and speed, compared to baseline approaches including exhaustive search, implicit-shape model (ISM), and efficient sub-window search (ESS). Moreover, we develop two extensions to consider non-rectangular bounding regions-composite boxes and polygons-and demonstrate their ability to achieve higher recognition scores compared to traditional rectangular bounding boxes. |
| first_indexed | 2024-09-23T16:44:08Z |
| format | Article |
| id | mit-1721.1/74258 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T16:44:08Z |
| publishDate | 2012 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/742582022-09-29T21:05:52Z Fast concurrent object localization and recognition Yeh, Tom Lee, John J. Darrell, Trevor J. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Yeh, Tom Object localization and recognition are important problems in computer vision. However, in many applications, exhaustive search over all object models and image locations is computationally prohibitive. While several methods have been proposed to make either recognition or localization more efficient, few have dealt with both tasks simultaneously. This paper proposes an efficient method for concurrent object localization and recognition based on a data-dependent multi-class branch-and-bound formalism. Existing bag-of-features recognition techniques which can be expressed as weighted combinations of feature counts can be readily adapted to our method. We present experimental results that demonstrate the merit of our algorithm in terms of recognition accuracy, localization accuracy, and speed, compared to baseline approaches including exhaustive search, implicit-shape model (ISM), and efficient sub-window search (ESS). Moreover, we develop two extensions to consider non-rectangular bounding regions-composite boxes and polygons-and demonstrate their ability to achieve higher recognition scores compared to traditional rectangular bounding boxes. 2012-10-25T19:08:40Z 2012-10-25T19:08:40Z 2009-08 2009-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-4244-3992-8 1063-6919 http://hdl.handle.net/1721.1/74258 Yeh, T., J.J. Lee, and T. Darrell. “Fast Concurrent Object Localization and Recognition.” IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE, 2009. 280–287. © Copyright 2009 IEEE en_US http://dx.doi.org/ 10.1109/CVPRW.2009.5206805 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009. Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. application/pdf Institute of Electrical and Electronics Engineers (IEEE) IEEE |
| spellingShingle | Yeh, Tom Lee, John J. Darrell, Trevor J. Fast concurrent object localization and recognition |
| title | Fast concurrent object localization and recognition |
| title_full | Fast concurrent object localization and recognition |
| title_fullStr | Fast concurrent object localization and recognition |
| title_full_unstemmed | Fast concurrent object localization and recognition |
| title_short | Fast concurrent object localization and recognition |
| title_sort | fast concurrent object localization and recognition |
| url | http://hdl.handle.net/1721.1/74258 |
| work_keys_str_mv | AT yehtom fastconcurrentobjectlocalizationandrecognition AT leejohnj fastconcurrentobjectlocalizationandrecognition AT darrelltrevorj fastconcurrentobjectlocalizationandrecognition |